© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1201
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bom
    -0.59
    hth
    -0.56
    ecore
    -0.55
    bom
    -0.52
    dom
    -0.52
     bomb
    -0.51
    IonicModule
    -0.51
    gom
    -0.51
    ograma
    -0.51
     strand
    -0.50
    POSITIVE LOGITS
    enumi
    0.79
    peu
    0.66
     peu
    0.61
     Peu
    0.58
    AsUp
    0.52
    peutic
    0.50
    UTERS
    0.49
     CreateTagHelper
    0.49
    rau
    0.47
    ascii
    0.46
    Activations Density 0.004%

    No Known Activations